thorwhalen

Code Generation Template Improvements

Summary

I've created three improved templates for your code generation use case, each with different levels of detail and structure. All are significant improvements over your original template.

---

Key Improvements Made

thorwhalen

"""
Vector Processing Pipeline Service

This module provides a FastAPI service for text segment processing through various
stages including embedding, clustering, and dimensionality reduction (planarization).

The service allows for:
- Individual processing of segments through specific stages
- Pipeline processing that combines multiple stages efficiently

thorwhalen

"""
This module defines a FastAPI application that demonstrates a simple pipeline
processing system. The system allows users to specify which stages they want
to include in the processing pipeline, and the system will automatically
compute and return the results for those stages.
"""

from fastapi import FastAPI, Depends, HTTPException
from pydantic import BaseModel
from typing import (

thorwhalen

from urllib.parse import urlparse 
import os
from functools import lru_cache


def ensure_raw_github_url(url):
    """
    This function takes a GitHub URL and returns the raw version of the URL.

    Args:

thorwhalen

# Note, the only two third party packages your need are:
#    pip install dol
#    pip install request

import os
import requests
from typing import Dict, Union, MutableMapping, KT, VT, TypeVar, Callable, Any
from functools import partial

thorwhalen

Extract Dev Meeting Takeaways from Video/Audio

The following code contains tools to get from video or audio to text and key takeaways for developers. Can be applied to video, audio or text, so can be used from meeting recordings, video demos, etc.

The following code is also meant to be a demo of the dol tools Pipe and written_key as well as the oa.prompt_function tool.

Requires dol, oa, speech_recognition and moviepy to be installed, though the last two are contained in functions and could be replaced.

thorwhalen

api_costs = {
    'gpt-4-1106-preview': {"input": 0.01, "output": 0.03, "unit": "$/1K tokens"},
    'gpt-4-1106-vision-preview': {"input": 0.01, "output": 0.03, "unit": "$/1K tokens"},
    'gpt-4': {"input": 0.03, "output": 0.06, "unit": "$/1K tokens"},
    'gpt-4-32k': {"input": 0.06, "output": 0.12, "unit": "$/1K tokens"},
    'gpt-3.5-turbo-1106': {"input": 0.0010, "output": 0.0020, "unit": "$/1K tokens"},
    'gpt-3.5-turbo-instruct': {"input": 0.0015, "output": 0.0020, "unit": "$/1K tokens"},
    'gpt-3.5-turbo': {"training": 0.0080, "input": 0.0030, "output": 0.0060, "unit": "$/1K tokens"},
    'davinci-002': {"training": 0.0060, "input": 0.0120, "output": 0.0120, "unit": "$/1K tokens"},
    'babbage-002': {"training": 0.0004, "input": 0.0016, "output": 0.0016, "unit": "$/1K tokens"},

thorwhalen

thorwhalen

from tested import validate_codec


Empty1 = type('Empty', (), {})()
print("\nEmpty1 = type('Empty', (), {})()")
print(f"{validate_codec(Empty1)=}")


_Empty2 = type('Empty', (), {})
_Empty2.__module__ = __name__

thorwhalen

# get raw df

import qo
df = qo.get_tables_from_url('https://en.wikipedia.org/wiki/List_of_salaries_of_heads_of_state_and_government')[3]
df = df.set_index('State')


# formatting and extracting salaries